Flight Lines
v0.1.0Navigate problems along lines of flight by composing operations from arbitrary domains. Operations are deterritorialized capacities—they don't belong to their origin domains. Mycorrhizal signaling + ham radio protocols + rare book dealer networks can compose into a single assemblage. The composer maintains parallel work-paths, constantly revising as new structure emerges.
⭐ 1· 1.8k·2 current·2 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name/description (composing operations across domains to solve problems) matches the SKILL.md content. There are no extra binaries, environment variables, or config paths required, so nothing requested is disproportionate to the stated purpose.
Instruction Scope
The runtime instructions are conceptual and describe a method (map terrain, identify structural constraints, query for operations from any domain, compose assemblages). They do not instruct reading files, environment variables, or calling external endpoints. However the guidance is intentionally open‑ended: an agent using this skill may ask for extensive personal/contextual information from the user to apply the method. Expect broad user prompts rather than any automatic system/resource access.
Install Mechanism
No install spec and no code files — instruction‑only. This is lowest risk (nothing is downloaded or written to disk).
Credentials
The skill requires no environment variables, credentials, or config paths. There is no disproportionate request for secrets or unrelated access.
Persistence & Privilege
always:false (default) and the skill does not request persistent/system privileges or modifications to other skills. Model invocation is allowed (default), which is normal for skills of this type.
Assessment
This skill is a philosophical/creative method, not a connector: it asks for nothing from your system and won't install code. It's coherent and low-risk technically, but it's deliberately broad — the agent may ask many personal or contextual questions to compose operations from disparate domains. If you want to limit exposure, keep responses high-level, decline to share sensitive secrets or system details, or disable autonomous invocation so the agent must ask before taking actions. If you expect the agent to call external services or read files, verify those behaviors separately (this skill does not specify them).Like a lobster shell, security has layers — review code before you run it.
latestvk97fnnrvezpegx757p8s94c7dn80bd4h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.